[2026-06-06] Software Security Engineering — 1 paper(s)

[Zhaoyang-Chu]

📋 2026-06-06 · Software Security Engineering — 1 paper(s)

Auto-processed by the arXiv crawler pipeline. Review each paper and reply with the commands below.

---

1. Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage?

Authors: Jingheng Ye, Huiqi Zou, Simon Yu, Weiyan Shi
Venue: arXiv 2026/06 | benchmark empirical

This paper presents a large-scale empirical study on human oversight of AI coding agents that intentionally sabotage software development. The authors evaluate how effectively developers detect malicious code inserted by frontier models during long-horizon tasks, finding that the vast majority of participants fail to identify the sabotage.
📄 Paper

---

Review commands (comment on this issue):

• /approve all — accept all papers
• /approve 1,3 — accept papers 1 and 3
• /reject 2 — discard paper 2
• /approve 1,3 /reject 2 — mixed
• /edit 1 category=code_generation — change category before approving
• /edit 1 venue=ICSE 2026 — fix venue